Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 265
• Descripción:
• Frecuencia: mes
• Variables: fecha_cnt, tmax, tmin, precip, longitud, latitud, altitud
• Dimensiones del mapa: 5,5
• Iteraciones: 1000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-265.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 1.244.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
1189 2982 5609 6382 2479 5674 2678 4529 3284 2654 4194 3319 5349 1601  345 7790 
  17   18   19   20   21   22   23   24   25 
1523 4312 2719 2839 4517 6144 3351 4280 5138 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "precip", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

       fecha_cnt       tmax       tmin      precip  longitud   latitud
[1,] 0.008548866 -0.8371435 -0.8606582  0.32885726 0.5039490 0.3118434
[2,] 0.811412845  0.4281654  0.3297262 -0.06266837 0.2547577 0.1482065
         altitud
[1,]  0.31464026
[2,] -0.05751936

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud      tmax   altitud      tmin   latitud fecha_cnt    precip 
0.9448887 0.9222487 0.9186947 0.9140405 0.9113429 0.9042962 0.8446315 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin           precip            nevada 
 Min.   : 1.0   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.0   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.0   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.5   Mean   :217.4   Mean   :150.7   Mean   :  6.856   Mean   :0  
 3rd Qu.: 9.0   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.0   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03089   Mean   :28.36   Mean   :-16.05   Mean   : 518.7  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.:147.0   1st Qu.:  50.00   1st Qu.:  3.00  
 Median : 6.000   Median :194.0   Median :  93.00   Median : 11.00  
 Mean   : 6.493   Mean   :199.1   Mean   :  94.91   Mean   : 16.45  
 3rd Qu.: 9.000   3rd Qu.:255.0   3rd Qu.: 141.00   3rd Qu.: 23.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.00   Max.   :128.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :28.48   Min.   :-17.7550  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:38.99   1st Qu.: -4.8500  
 Median :0.000000   Median :   0.0000   Median :40.96   Median : -2.4831  
 Mean   :0.000319   Mean   :   0.4811   Mean   :40.54   Mean   : -2.4366  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.22   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :1834.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 251.0  
 Mean   : 410.5  
 3rd Qu.: 667.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   : -8.0   Min.   :-58.00   Min.   :106.0   Min.   :0  
 1st Qu.: 2.00   1st Qu.:112.0   1st Qu.: 48.00   1st Qu.:128.0   1st Qu.:0  
 Median :10.00   Median :133.0   Median : 71.00   Median :139.0   Median :0  
 Mean   : 7.47   Mean   :135.8   Mean   : 71.68   Mean   :151.4   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:158.0   3rd Qu.: 95.00   3rd Qu.:160.0   3rd Qu.:0  
 Max.   :12.00   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.29   1st Qu.: -8.624   1st Qu.:  87.0  
 Median :  0.000   Median :42.38   Median : -8.411   Median : 261.0  
 Mean   :  5.539   Mean   :41.34   Mean   : -6.249   Mean   : 468.9  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -3.831   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  2.827   Max.   :2400.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin           precip            nevada 
 Min.   : 1.0   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.0   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.0   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.5   Mean   :217.4   Mean   :150.7   Mean   :  6.856   Mean   :0  
 3rd Qu.: 9.0   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.0   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03089   Mean   :28.36   Mean   :-16.05   Mean   : 518.7  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax          tmin             precip      
 Min.   : 1.000   Min.   :-53   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 2.000   1st Qu.:127   1st Qu.:  32.00   1st Qu.:  6.00  
 Median : 4.000   Median :161   Median :  64.00   Median : 14.00  
 Mean   : 5.906   Mean   :159   Mean   :  62.22   Mean   : 19.66  
 3rd Qu.:10.000   3rd Qu.:193   3rd Qu.:  93.00   3rd Qu.: 27.00  
 Max.   :12.000   Max.   :336   Max.   : 219.00   Max.   :128.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :28.48   Min.   :-17.7550  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:38.99   1st Qu.: -4.8500  
 Median :0.000000   Median :   0.0000   Median :40.96   Median : -2.4831  
 Mean   :0.000488   Mean   :   0.7336   Mean   :40.58   Mean   : -2.4385  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.24   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :1834.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  47.0  
 Median : 286.0  
 Mean   : 451.9  
 3rd Qu.: 687.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 4.000   Min.   :149.0   Min.   : 49.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 7.000   1st Qu.:247.0   1st Qu.:132.0   1st Qu.: 1.00   1st Qu.:0  
 Median : 8.000   Median :276.0   Median :156.0   Median : 6.00   Median :0  
 Mean   : 7.605   Mean   :275.2   Mean   :156.9   Mean   :10.37   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:303.0   3rd Qu.:182.0   3rd Qu.:15.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :78.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500   1st Qu.:  43.0  
 Median : 0.00000   Median :40.93   Median :-2.4831   Median : 185.0  
 Mean   : 0.00251   Mean   :40.47   Mean   :-2.4328   Mean   : 331.9  
 3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4942   3rd Qu.: 611.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   : -8.0   Min.   :-58.00   Min.   :106.0   Min.   :0  
 1st Qu.: 2.00   1st Qu.:112.0   1st Qu.: 48.00   1st Qu.:128.0   1st Qu.:0  
 Median :10.00   Median :133.0   Median : 71.00   Median :139.0   Median :0  
 Mean   : 7.47   Mean   :135.8   Mean   : 71.68   Mean   :151.4   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:158.0   3rd Qu.: 95.00   3rd Qu.:160.0   3rd Qu.:0  
 Max.   :12.00   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.29   1st Qu.: -8.624   1st Qu.:  87.0  
 Median :  0.000   Median :42.38   Median : -8.411   Median : 261.0  
 Mean   :  5.539   Mean   :41.34   Mean   : -6.249   Mean   : 468.9  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -3.831   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  2.827   Max.   :2400.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin           precip            nevada 
 Min.   : 1.0   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.0   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.0   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.5   Mean   :217.4   Mean   :150.7   Mean   :  6.856   Mean   :0  
 3rd Qu.: 9.0   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.0   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03089   Mean   :28.36   Mean   :-16.05   Mean   : 518.7  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 2.000   1st Qu.:127.0   1st Qu.:  27.00   1st Qu.:  5.00  
 Median : 3.000   Median :162.0   Median :  61.00   Median : 13.00  
 Mean   : 3.265   Mean   :158.7   Mean   :  58.78   Mean   : 16.19  
 3rd Qu.: 4.000   3rd Qu.:194.0   3rd Qu.:  90.00   3rd Qu.: 24.00  
 Max.   :12.000   Max.   :321.0   Max.   : 191.00   Max.   :126.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   :   0.000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:38.99   1st Qu.:-4.7667  
 Median :0.000000   Median :   0.000   Median :40.96   Median :-2.3308  
 Mean   :0.000529   Mean   :   1.138   Mean   :40.51   Mean   :-2.1760  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.12   3rd Qu.: 0.7106  
 Max.   :6.000000   Max.   :1834.000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  47.0  
 Median : 286.0  
 Mean   : 483.1  
 3rd Qu.: 704.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 4.000   Min.   :149.0   Min.   : 49.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 7.000   1st Qu.:247.0   1st Qu.:132.0   1st Qu.: 1.00   1st Qu.:0  
 Median : 8.000   Median :276.0   Median :156.0   Median : 6.00   Median :0  
 Mean   : 7.605   Mean   :275.2   Mean   :156.9   Mean   :10.37   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:303.0   3rd Qu.:182.0   3rd Qu.:15.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :78.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500   1st Qu.:  43.0  
 Median : 0.00000   Median :40.93   Median :-2.4831   Median : 185.0  
 Mean   : 0.00251   Mean   :40.47   Mean   :-2.4328   Mean   : 331.9  
 3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4942   3rd Qu.: 611.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin          precip      
 Min.   : 1.00   Min.   :  8.0   Min.   :-110   Min.   :  0.00  
 1st Qu.:10.00   1st Qu.:126.0   1st Qu.:  40   1st Qu.:  7.00  
 Median :11.00   Median :159.0   Median :  70   Median : 17.00  
 Mean   :10.33   Mean   :159.5   Mean   :  68   Mean   : 25.48  
 3rd Qu.:12.00   3rd Qu.:192.0   3rd Qu.:  97   3rd Qu.: 37.00  
 Max.   :12.00   Max.   :336.0   Max.   : 219   Max.   :128.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   : 0.00000   Min.   :28.48   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:39.47   1st Qu.: -5.5975  
 Median :0.0000000   Median : 0.00000   Median :41.11   Median : -3.4503  
 Mean   :0.0004196   Mean   : 0.05585   Mean   :40.69   Mean   : -2.8785  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.36   3rd Qu.:  0.0714  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  58.0  
 Median : 286.0  
 Mean   : 399.7  
 3rd Qu.: 667.0  
 Max.   :1894.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   : -8.0   Min.   :-58.00   Min.   :106.0   Min.   :0  
 1st Qu.: 2.00   1st Qu.:112.0   1st Qu.: 48.00   1st Qu.:128.0   1st Qu.:0  
 Median :10.00   Median :133.0   Median : 71.00   Median :139.0   Median :0  
 Mean   : 7.47   Mean   :135.8   Mean   : 71.68   Mean   :151.4   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:158.0   3rd Qu.: 95.00   3rd Qu.:160.0   3rd Qu.:0  
 Max.   :12.00   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.29   1st Qu.: -8.624   1st Qu.:  87.0  
 Median :  0.000   Median :42.38   Median : -8.411   Median : 261.0  
 Mean   :  5.539   Mean   :41.34   Mean   : -6.249   Mean   : 468.9  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -3.831   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  2.827   Max.   :2400.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt         tmax            tmin           precip            nevada 
 Min.   : 1.0   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.0   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.0   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.5   Mean   :217.4   Mean   :150.7   Mean   :  6.856   Mean   :0  
 3rd Qu.: 9.0   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.0   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03089   Mean   :28.36   Mean   :-16.05   Mean   : 518.7  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip     
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:134.0   1st Qu.: 32.00   1st Qu.: 5.00  
 Median :3.000   Median :165.0   Median : 63.00   Median :12.00  
 Mean   :3.035   Mean   :165.1   Mean   : 62.77   Mean   :14.71  
 3rd Qu.:4.000   3rd Qu.:196.0   3rd Qu.: 92.00   3rd Qu.:22.00  
 Max.   :7.000   Max.   :321.0   Max.   :191.00   Max.   :69.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   :  0.0000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:38.88   1st Qu.:-4.8500  
 Median :0.000000   Median :  0.0000   Median :40.95   Median :-2.4544  
 Mean   :0.000568   Mean   :  0.0929   Mean   :40.40   Mean   :-2.3382  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:41.98   3rd Qu.: 0.4942  
 Max.   :6.000000   Max.   :117.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  43.3  
 Median : 247.0  
 Mean   : 359.3  
 3rd Qu.: 639.0  
 Max.   :1894.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin              precip      
 Min.   : 1.00   Min.   :-53.00   Min.   :-121.000   Min.   :  0.00  
 1st Qu.: 3.00   1st Qu.: 27.00   1st Qu.: -35.000   1st Qu.: 20.00  
 Median : 6.00   Median : 66.00   Median :   0.000   Median : 32.00  
 Mean   : 6.37   Mean   : 72.62   Mean   :   4.922   Mean   : 36.18  
 3rd Qu.:10.00   3rd Qu.:117.00   3rd Qu.:  45.000   3rd Qu.: 48.00  
 Max.   :12.00   Max.   :218.00   Max.   : 128.000   Max.   :126.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.01030  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:41.77   1st Qu.: 0.72920  
 Median :0   Median :   0.00   Median :42.47   Median : 0.98440  
 Mean   :0   Mean   :  15.25   Mean   :42.05   Mean   : 0.01392  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.: 1.52420  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.43780  
    altitud    
 Min.   :1167  
 1st Qu.:1894  
 Median :2230  
 Mean   :2155  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 4.000   Min.   :149.0   Min.   : 49.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 7.000   1st Qu.:247.0   1st Qu.:132.0   1st Qu.: 1.00   1st Qu.:0  
 Median : 8.000   Median :276.0   Median :156.0   Median : 6.00   Median :0  
 Mean   : 7.605   Mean   :275.2   Mean   :156.9   Mean   :10.37   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:303.0   3rd Qu.:182.0   3rd Qu.:15.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :78.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500   1st Qu.:  43.0  
 Median : 0.00000   Median :40.93   Median :-2.4831   Median : 185.0  
 Mean   : 0.00251   Mean   :40.47   Mean   :-2.4328   Mean   : 331.9  
 3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4942   3rd Qu.: 611.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin          precip      
 Min.   : 1.00   Min.   :  8.0   Min.   :-110   Min.   :  0.00  
 1st Qu.:10.00   1st Qu.:126.0   1st Qu.:  40   1st Qu.:  7.00  
 Median :11.00   Median :159.0   Median :  70   Median : 17.00  
 Mean   :10.33   Mean   :159.5   Mean   :  68   Mean   : 25.48  
 3rd Qu.:12.00   3rd Qu.:192.0   3rd Qu.:  97   3rd Qu.: 37.00  
 Max.   :12.00   Max.   :336.0   Max.   : 219   Max.   :128.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   : 0.00000   Min.   :28.48   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:39.47   1st Qu.: -5.5975  
 Median :0.0000000   Median : 0.00000   Median :41.11   Median : -3.4503  
 Mean   :0.0004196   Mean   : 0.05585   Mean   :40.69   Mean   : -2.8785  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:42.36   3rd Qu.:  0.0714  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  58.0  
 Median : 286.0  
 Mean   : 399.7  
 3rd Qu.: 667.0  
 Max.   :1894.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   : -8.0   Min.   :-58.00   Min.   :106.0   Min.   :0  
 1st Qu.: 2.00   1st Qu.:112.0   1st Qu.: 48.00   1st Qu.:128.0   1st Qu.:0  
 Median :10.00   Median :133.0   Median : 71.00   Median :139.0   Median :0  
 Mean   : 7.47   Mean   :135.8   Mean   : 71.68   Mean   :151.4   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:158.0   3rd Qu.: 95.00   3rd Qu.:160.0   3rd Qu.:0  
 Max.   :12.00   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.29   1st Qu.: -8.624   1st Qu.:  87.0  
 Median :  0.000   Median :42.38   Median : -8.411   Median : 261.0  
 Mean   :  5.539   Mean   :41.34   Mean   : -6.249   Mean   : 468.9  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -3.831   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  2.827   Max.   :2400.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94.0   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :129.0   Median : 51.00   Median :  3.00   Median :0  
 Mean   : 6.585   Mean   :138.4   Mean   : 60.83   Mean   : 10.29   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183.0   3rd Qu.: 98.00   3rd Qu.: 13.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253.0   Max.   :159.00   Max.   :114.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1766   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin            precip     
 Min.   :1.000   Min.   : -4.0   Min.   :-89.00   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:134.0   1st Qu.: 32.00   1st Qu.: 5.00  
 Median :3.000   Median :165.0   Median : 63.00   Median :12.00  
 Mean   :3.035   Mean   :165.1   Mean   : 62.77   Mean   :14.71  
 3rd Qu.:4.000   3rd Qu.:196.0   3rd Qu.: 92.00   3rd Qu.:22.00  
 Max.   :7.000   Max.   :321.0   Max.   :191.00   Max.   :69.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   :  0.0000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:38.88   1st Qu.:-4.8500  
 Median :0.000000   Median :  0.0000   Median :40.95   Median :-2.4544  
 Mean   :0.000568   Mean   :  0.0929   Mean   :40.40   Mean   :-2.3382  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:41.98   3rd Qu.: 0.4942  
 Max.   :6.000000   Max.   :117.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  43.3  
 Median : 247.0  
 Mean   : 359.3  
 3rd Qu.: 639.0  
 Max.   :1894.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin              precip      
 Min.   : 1.00   Min.   :-53.00   Min.   :-121.000   Min.   :  0.00  
 1st Qu.: 3.00   1st Qu.: 27.00   1st Qu.: -35.000   1st Qu.: 20.00  
 Median : 6.00   Median : 66.00   Median :   0.000   Median : 32.00  
 Mean   : 6.37   Mean   : 72.62   Mean   :   4.922   Mean   : 36.18  
 3rd Qu.:10.00   3rd Qu.:117.00   3rd Qu.:  45.000   3rd Qu.: 48.00  
 Max.   :12.00   Max.   :218.00   Max.   : 128.000   Max.   :126.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.01030  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:41.77   1st Qu.: 0.72920  
 Median :0   Median :   0.00   Median :42.47   Median : 0.98440  
 Mean   :0   Mean   :  15.25   Mean   :42.05   Mean   : 0.01392  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.: 1.52420  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.43780  
    altitud    
 Min.   :1167  
 1st Qu.:1894  
 Median :2230  
 Mean   :2155  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax          tmin           precip           nevada 
 Min.   : 1.000   Min.   : 87   Min.   : 64.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 3.000   1st Qu.:212   1st Qu.:150.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 6.000   Median :233   Median :168.0   Median : 1.000   Median :0  
 Mean   : 6.482   Mean   :234   Mean   :169.5   Mean   : 6.136   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:259   3rd Qu.:196.0   3rd Qu.: 7.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356   Max.   :244.0   Max.   :89.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003525   Mean   :28.38   Mean   :-15.95   Mean   :130.5  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 4.000   Min.   :149.0   Min.   : 49.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 7.000   1st Qu.:247.0   1st Qu.:132.0   1st Qu.: 1.00   1st Qu.:0  
 Median : 8.000   Median :276.0   Median :156.0   Median : 6.00   Median :0  
 Mean   : 7.605   Mean   :275.2   Mean   :156.9   Mean   :10.37   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:303.0   3rd Qu.:182.0   3rd Qu.:15.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :78.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500   1st Qu.:  43.0  
 Median : 0.00000   Median :40.93   Median :-2.4831   Median : 185.0  
 Mean   : 0.00251   Mean   :40.47   Mean   :-2.4328   Mean   : 331.9  
 3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4942   3rd Qu.: 611.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 57.0   Min.   :-25.0   Min.   :  5.00   Min.   :0  
 1st Qu.: 5.000   1st Qu.:128.0   1st Qu.: 57.0   1st Qu.: 43.00   1st Qu.:0  
 Median :11.000   Median :149.0   Median : 76.0   Median : 57.00   Median :0  
 Mean   : 8.602   Mean   :153.2   Mean   : 79.2   Mean   : 59.13   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:175.0   3rd Qu.: 99.0   3rd Qu.: 73.00   3rd Qu.:0  
 Max.   :12.000   Max.   :336.0   Max.   :219.0   Max.   :128.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :28.48   Min.   :-17.755   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:41.98   1st Qu.: -7.860   1st Qu.:  42.0  
 Median : 0.00000   Median :42.89   Median : -5.598   Median : 108.0  
 Mean   : 0.06743   Mean   :42.04   Mean   : -4.767   Mean   : 214.7  
 3rd Qu.: 0.00000   3rd Qu.:43.36   3rd Qu.: -2.654   3rd Qu.: 370.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.216   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   : -8.0   Min.   :-58.00   Min.   :106.0   Min.   :0  
 1st Qu.: 2.00   1st Qu.:112.0   1st Qu.: 48.00   1st Qu.:128.0   1st Qu.:0  
 Median :10.00   Median :133.0   Median : 71.00   Median :139.0   Median :0  
 Mean   : 7.47   Mean   :135.8   Mean   : 71.68   Mean   :151.4   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:158.0   3rd Qu.: 95.00   3rd Qu.:160.0   3rd Qu.:0  
 Max.   :12.00   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.29   1st Qu.: -8.624   1st Qu.:  87.0  
 Median :  0.000   Median :42.38   Median : -8.411   Median : 261.0  
 Mean   :  5.539   Mean   :41.34   Mean   : -6.249   Mean   : 468.9  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -3.831   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  2.827   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin            precip     
 Min.   : 6.00   Min.   :  8.0   Min.   :-110.0   Min.   : 0.00  
 1st Qu.:10.00   1st Qu.:125.0   1st Qu.:  31.0   1st Qu.: 4.00  
 Median :11.00   Median :166.0   Median :  66.0   Median :11.00  
 Mean   :10.98   Mean   :161.8   Mean   :  63.8   Mean   :12.89  
 3rd Qu.:12.00   3rd Qu.:198.0   3rd Qu.:  96.0   3rd Qu.:19.00  
 Max.   :12.00   Max.   :305.0   Max.   : 189.0   Max.   :55.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.4881  
 Median :0.0000000   Median : 0.00000   Median :40.78   Median :-2.3567  
 Mean   :0.0005766   Mean   : 0.05151   Mean   :40.19   Mean   :-2.1716  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:41.67   3rd Qu.: 0.4942  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  71.0  
 Median : 510.0  
 Mean   : 468.9  
 3rd Qu.: 779.0  
 Max.   :1894.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94.0   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :129.0   Median : 51.00   Median :  3.00   Median :0  
 Mean   : 6.585   Mean   :138.4   Mean   : 60.83   Mean   : 10.29   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183.0   3rd Qu.: 98.00   3rd Qu.: 13.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253.0   Max.   :159.00   Max.   :114.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1766   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin         precip    
 Min.   :1.000   Min.   : 58.0   Min.   :-41   Min.   : 0.0  
 1st Qu.:2.000   1st Qu.:161.0   1st Qu.: 59   1st Qu.: 3.0  
 Median :3.000   Median :186.0   Median : 87   Median : 8.0  
 Mean   :3.159   Mean   :189.4   Mean   : 87   Mean   :10.7  
 3rd Qu.:4.000   3rd Qu.:218.0   3rd Qu.:115   3rd Qu.:16.0  
 Max.   :7.000   Max.   :321.0   Max.   :191   Max.   :55.0  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-6.9492  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.:-4.8458  
 Median :0.0000000   Median : 0.00000   Median :38.88   Median : 0.0714  
 Mean   :0.0002532   Mean   : 0.02538   Mean   :39.16   Mean   :-1.3112  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:41.29   3rd Qu.: 1.1678  
 Max.   :2.0000000   Max.   :40.00000   Max.   :43.49   Max.   : 4.2156  
    altitud     
 Min.   :  1.0  
 1st Qu.: 19.0  
 Median : 53.0  
 Mean   :109.2  
 3rd Qu.:143.0  
 Max.   :816.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin           precip     
 Min.   :1.000   Min.   : -4.0   Min.   :-89.0   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:112.0   1st Qu.: 14.0   1st Qu.: 7.00  
 Median :3.000   Median :145.0   Median : 42.0   Median :16.00  
 Mean   :2.923   Mean   :143.3   Mean   : 41.1   Mean   :18.29  
 3rd Qu.:4.000   3rd Qu.:174.0   3rd Qu.: 69.0   3rd Qu.:27.00  
 Max.   :6.000   Max.   :256.0   Max.   :131.0   Max.   :69.00  
     nevada           prof_nieve          longitud        latitud      
 Min.   :0.000000   Min.   :  0.0000   Min.   :37.13   Min.   :-8.649  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:40.48   1st Qu.:-4.850  
 Median :0.000000   Median :  0.0000   Median :41.65   Median :-3.678  
 Mean   :0.000849   Mean   :  0.1533   Mean   :41.50   Mean   :-3.256  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:42.59   3rd Qu.:-1.861  
 Max.   :6.000000   Max.   :117.0000   Max.   :43.57   Max.   : 4.216  
    altitud    
 Min.   :   1  
 1st Qu.: 353  
 Median : 627  
 Mean   : 583  
 3rd Qu.: 846  
 Max.   :1894  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax             tmin              precip      
 Min.   : 1.00   Min.   :-53.00   Min.   :-121.000   Min.   :  0.00  
 1st Qu.: 3.00   1st Qu.: 27.00   1st Qu.: -35.000   1st Qu.: 20.00  
 Median : 6.00   Median : 66.00   Median :   0.000   Median : 32.00  
 Mean   : 6.37   Mean   : 72.62   Mean   :   4.922   Mean   : 36.18  
 3rd Qu.:10.00   3rd Qu.:117.00   3rd Qu.:  45.000   3rd Qu.: 48.00  
 Max.   :12.00   Max.   :218.00   Max.   : 128.000   Max.   :126.00  
     nevada    prof_nieve         longitud        latitud        
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.01030  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:41.77   1st Qu.: 0.72920  
 Median :0   Median :   0.00   Median :42.47   Median : 0.98440  
 Mean   :0   Mean   :  15.25   Mean   :42.05   Mean   : 0.01392  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.: 1.52420  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.43780  
    altitud    
 Min.   :1167  
 1st Qu.:1894  
 Median :2230  
 Mean   :2155  
 3rd Qu.:2400  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax          tmin           precip           nevada 
 Min.   : 1.000   Min.   : 87   Min.   : 64.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 3.000   1st Qu.:212   1st Qu.:150.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 6.000   Median :233   Median :168.0   Median : 1.000   Median :0  
 Mean   : 6.482   Mean   :234   Mean   :169.5   Mean   : 6.136   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:259   3rd Qu.:196.0   3rd Qu.: 7.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356   Max.   :244.0   Max.   :89.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003525   Mean   :28.38   Mean   :-15.95   Mean   :130.5  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 4.000   Min.   :149.0   Min.   : 49.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 7.000   1st Qu.:247.0   1st Qu.:132.0   1st Qu.: 1.00   1st Qu.:0  
 Median : 8.000   Median :276.0   Median :156.0   Median : 6.00   Median :0  
 Mean   : 7.605   Mean   :275.2   Mean   :156.9   Mean   :10.37   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:303.0   3rd Qu.:182.0   3rd Qu.:15.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :78.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500   1st Qu.:  43.0  
 Median : 0.00000   Median :40.93   Median :-2.4831   Median : 185.0  
 Mean   : 0.00251   Mean   :40.47   Mean   :-2.4328   Mean   : 331.9  
 3rd Qu.: 0.00000   3rd Qu.:42.08   3rd Qu.: 0.4942   3rd Qu.: 611.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :1.000   Min.   : 57.0   Min.   :-22.00   Min.   : 46.00   Min.   :0  
 1st Qu.:1.000   1st Qu.:120.0   1st Qu.: 50.00   1st Qu.: 58.00   1st Qu.:0  
 Median :2.000   Median :139.0   Median : 67.00   Median : 66.00   Median :0  
 Mean   :2.488   Mean   :139.8   Mean   : 66.77   Mean   : 70.21   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:158.0   3rd Qu.: 83.00   3rd Qu.: 79.00   3rd Qu.:0  
 Max.   :6.000   Max.   :245.0   Max.   :150.00   Max.   :120.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   : 0.0000   Min.   :28.48   Min.   :-17.755   Min.   :   1.0  
 1st Qu.: 0.0000   1st Qu.:42.24   1st Qu.: -8.411   1st Qu.:  34.0  
 Median : 0.0000   Median :42.89   Median : -5.698   Median : 108.0  
 Mean   : 0.1012   Mean   :42.08   Mean   : -5.262   Mean   : 180.1  
 3rd Qu.: 0.0000   3rd Qu.:43.36   3rd Qu.: -2.906   3rd Qu.: 261.0  
 Max.   :35.0000   Max.   :43.57   Max.   :  3.182   Max.   :1572.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 1.00   Min.   : -8.0   Min.   :-58.00   Min.   :106.0   Min.   :0  
 1st Qu.: 2.00   1st Qu.:112.0   1st Qu.: 48.00   1st Qu.:128.0   1st Qu.:0  
 Median :10.00   Median :133.0   Median : 71.00   Median :139.0   Median :0  
 Mean   : 7.47   Mean   :135.8   Mean   : 71.68   Mean   :151.4   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:158.0   3rd Qu.: 95.00   3rd Qu.:160.0   3rd Qu.:0  
 Max.   :12.00   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.29   1st Qu.: -8.624   1st Qu.:  87.0  
 Median :  0.000   Median :42.38   Median : -8.411   Median : 261.0  
 Mean   :  5.539   Mean   :41.34   Mean   : -6.249   Mean   : 468.9  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -3.831   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  2.827   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 5.00   Min.   : 59.0   Min.   :-25.0   Min.   :  5.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:133.0   1st Qu.: 60.0   1st Qu.: 38.00   1st Qu.:0  
 Median :11.00   Median :154.0   Median : 81.0   Median : 51.00   Median :0  
 Mean   :10.91   Mean   :158.2   Mean   : 83.9   Mean   : 54.95   Mean   :0  
 3rd Qu.:12.00   3rd Qu.:181.0   3rd Qu.:105.8   3rd Qu.: 69.00   3rd Qu.:0  
 Max.   :12.00   Max.   :336.0   Max.   :219.0   Max.   :128.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :28.48   Min.   :-17.755   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:41.67   1st Qu.: -7.456   1st Qu.:  42.0  
 Median : 0.00000   Median :42.89   Median : -4.846   Median : 127.0  
 Mean   : 0.05469   Mean   :42.03   Mean   : -4.580   Mean   : 227.7  
 3rd Qu.: 0.00000   3rd Qu.:43.36   3rd Qu.: -2.039   3rd Qu.: 370.0  
 Max.   :27.00000   Max.   :43.57   Max.   :  4.216   Max.   :1405.0  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt          tmax            tmin            precip     
 Min.   : 6.00   Min.   :  8.0   Min.   :-110.0   Min.   : 0.00  
 1st Qu.:10.00   1st Qu.:125.0   1st Qu.:  31.0   1st Qu.: 4.00  
 Median :11.00   Median :166.0   Median :  66.0   Median :11.00  
 Mean   :10.98   Mean   :161.8   Mean   :  63.8   Mean   :12.89  
 3rd Qu.:12.00   3rd Qu.:198.0   3rd Qu.:  96.0   3rd Qu.:19.00  
 Max.   :12.00   Max.   :305.0   Max.   : 189.0   Max.   :55.00  
     nevada            prof_nieve          longitud        latitud       
 Min.   :0.0000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.0000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.4881  
 Median :0.0000000   Median : 0.00000   Median :40.78   Median :-2.3567  
 Mean   :0.0005766   Mean   : 0.05151   Mean   :40.19   Mean   :-2.1716  
 3rd Qu.:0.0000000   3rd Qu.: 0.00000   3rd Qu.:41.67   3rd Qu.: 0.4942  
 Max.   :3.0000000   Max.   :59.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  71.0  
 Median : 510.0  
 Mean   : 468.9  
 3rd Qu.: 779.0  
 Max.   :1894.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)